Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 658 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.9179. Min Act: -0.0001

Data Index: 207053 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.9265. Min Act: -0.0001

Data Index: 170341 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8994. Min Act: -0.0001

Data Index: 59045 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.9409. Min Act: -0.0001

Data Index: 163568 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8339. Min Act: -0.0001

Data Index: 796744 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8126. Min Act: -0.0001

Data Index: 968823 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.8181. Min Act: -0.0001

Data Index: 1153068 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7763. Min Act: -0.0001

Data Index: 590656 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7640. Min Act: -0.0001

Data Index: 315934 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7864. Min Act: -0.0001

Data Index: 737306 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7493. Min Act: -0.0001

Data Index: 984516 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7340. Min Act: -0.0001

Data Index: 853913 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6710. Min Act: -0.0001

Data Index: 915355 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7128. Min Act: -0.0001

Data Index: 528937 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7791. Min Act: -0.0001

Data Index: 1187229 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7195. Min Act: -0.0001

Data Index: 697183 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.7039. Min Act: -0.0001

Data Index: 123584 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6910. Min Act: -0.0001

Data Index: 1064386 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6689. Min Act: -0.0001

Data Index: 693515 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.9409. Min Range: -0.9409

Max Act: 0.6613. Min Act: -0.0001

Data Index: 1298751 (C4 (Web Text))

Max Activating Token Index: 991